Bounds on margin distributions in learning problems

MaRDI QIDQ1413099zbMATH OpenFDO

Authors Vladimir Koltchinskii

Publication date 16 November 2003

Published in Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)

Full work available at URL http://www.numdam.org/item?id=AIHPB_2003__39_6_943_0, https://eudml.org/doc/77791

zbMATH Keywords

machine learningerror of learning algorithms

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Inequalities; stochastic orderings (60E15)

Recommendations

• scientific article; zbMATH DE number 1804114
• 10.1162/153244303768966111
• Distribution-dependent sample complexity of large margin learning
• Risk bounds for statistical learning
• Empirical margin distributions and bounding the generalization error of combined classifiers
• A PAC-Bayesian margin bound for linear classifiers
• Learning bounds via sample width for classifiers on finite metric spaces
• Advances in Neural Networks – ISNN 2005

Cited in

(10)

• Computing and Combinatorics
• Learning Theory
• Bounding the generalization error of convex combinations of classifiers: Balancing the dimensionality and the margins.
• Complexities of convex combinations and bounding the generalization error in classification
• Local entropy in learning theory
• Continuity of Performance Metrics for Thin Feature Maps
• The entropy in learning theory. Error estimates
• Concentration inequalities and asymptotic results for ratio type empirical processes
• scientific article; zbMATH DE number 1552503 (Why is no real title available?)
• Empirical approximation of the Gaussian distribution in \(\mathbb{R}^d\)

This page was built for publication: Bounds on margin distributions in learning problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1413099)